Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    variations of the word "summit" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ough
    -0.18
    -gnu
    -0.16
    antage
    -0.16
    onom
    -0.16
    qm
    -0.15
    coni
    -0.15
    caf
    -0.15
    pool
    -0.15
    inh
    -0.15
    anz
    -0.15
    POSITIVE LOGITS
    ption
    0.24
    maries
    0.23
    ming
    0.23
    mand
    0.22
    ptions
    0.20
    mers
    0.19
    .Sum
    0.17
    erged
    0.17
    MARY
    0.17
    ertime
    0.17
    Act Density 0.021%

    No Known Activations